Example output from DeOldify

Machine Learning in Linux: DeOldify – colorizing and restoring old images and videos

Last Updated on May 5, 2023

DeOldify is a modern way to colorize black and white images using deep learning technology. The software provides pre-trained weights which allows you to colorize images and video without needing to train your own models.

Our Machine Learning in Linux series focuses on apps that make it easy to experiment with machine learning. This article is a bit different. We wouldn’t describe DeOoldify as an app. But it’s a very interesting project and bills itself as the easiest way to colorize images.

DeOldify is published under an open source license.

Installation

First clone the project’s GitHub repository.

$ git clone https://github.com/jantic/DeOldify

Change into the newly created environment.

$ cd DeOldify

Using conda, create a virtual environment (to avoid polluting your system) with the command. You’ll need Anaconda or miniconda installed (for the conda command).

$ conda env create -f environment.yml

At the end of the installation, you’ll see output like:

Successfully built pathtools
Installing collected packages: pathtools, brotli, appdirs, websockets, smmap, setproctitle, sentry-sdk, pycryptodomex, opencv-python, mutagen, ffmpeg-python, docker-pycreds, yt-dlp, gitdb, GitPython, wandb
Successfully installed GitPython-3.1.31 appdirs-1.4.4 brotli-1.0.9 docker-pycreds-0.4.0 ffmpeg-python-0.2.0 gitdb-4.0.10 mutagen-1.46.0 opencv-python-4.7.0.72 pathtools-0.1.2 pycryptodomex-3.17 sentry-sdk-1.18.0 setproctitle-1.3.2 smmap-5.0.0 wandb-0.14.0 websockets-10.4 yt-dlp-2023.3.4

Unless you’re going to train your own models, you’ll need to download one or more of the pre-trained models available. The models (Completed Generator Weights) are available from the project’s GitHub. Copy the modules to the DeOldify/models directory.

DeOldify models

Start the virtual environment with the command:

$ source activate deoldify

Next page: Page 2 – In Operation and Summary

Pages in this article:
Page 1 – Introduction and Installation
Page 2 – In Operation and Summary

Subscribe
Notify of
guest

This site uses Akismet to reduce spam. Learn how your comment data is processed.

0 Comments
Oldest
Newest Most Voted
Inline Feedbacks
View all comments